---
title: "Explore Housing and Electricity Relationship in LA"
output:
flexdashboard::flex_dashboard:
storyboard: true
social: menu
source: embed
---
```{r setup, include=FALSE}
library(flexdashboard)
```
```{r}
library(tidyverse)
library(ggplot2)
library(scales)
library(viridis)
library(igraph)
library(plotly)
library(sp)
library(maps)
library(maptools)
library(wordcloud2)
library(tm)
library(SnowballC)
library(wordcloud)
library(RColorBrewer)
Sys.setenv(MAPBOX_TOKEN = 11122223333444)
```
```{r}
electricity = read.csv("Electricity.csv")
groupbys <- electricity %>%
select('Owner', 'County', 'Highest_kV') %>%
group_by(County) %>%
drop_na()
groupbys['weight'] <- as.numeric(factor(groupbys[['Highest_kV']]))
groupbys <- groupbys %>%
select('Owner', 'County', 'weight')
groupbys <- groupbys %>%
filter(County %in% c('Los Angeles', 'San Diego',
'Orange', 'Riverside', 'San Bernardino',
'Santa Clara', 'Sacramento', 'San Francisco',
'Kern', 'Fresno'))
graphdf <- groupbys %>%
group_by(Owner, County) %>%
summarize(total_weight = sum(weight))
graphdf <- graphdf %>% drop_na()
```
### ABOUT
Graph1: shows that among all the power station provider, the top electricity demand city is LA.
Graph2: shows top 10 cities' relationship between electricity consumption and housing prices in CA
Graph3: shows that before 2010, the electricity consumption grows with year, and after 2010, the electricity consumption in LA become stable.
Graph4: LA housing price distribution with local region income median and population.
Graph5: The distribution of housing prices among different ocean proximity in LA.
Graph6: The wordcloud generated from related news and article.
Dataset & Reference:
1. https://www.kaggle.com/camnugent/california-housing-prices
2. http://www.ecdms.energy.ca.gov/elecbycounty.aspx
3. https://www.noradarealestate.com/blog/los-angeles-real-estate-market/
4. https://cecgis-caenergy.opendata.arcgis.com/datasets/7f37f2535d3144e898a53b9385737ee0_0/data?geometry=-160.990%2C31.125%2C-77.362%2C43.323
### Graph1: The network relationship between electricity station owner and top 10 CA cities.
```{r}
graphdf1 <- graph_from_data_frame(graphdf, directed = TRUE)
V(graphdf1)[1:10]$colour = 'gray'
V(graphdf1)[10]$colour = 'chocolate'
V(graphdf1)[11]$colour = 'chocolate1'
V(graphdf1)[12]$colour = 'chocolate2'
V(graphdf1)[13]$colour = 'chocolate3'
V(graphdf1)[14]$colour = 'coral'
V(graphdf1)[15]$colour = 'coral1'
V(graphdf1)[16]$colour = 'coral2'
V(graphdf1)[17]$colour = 'coral3'
V(graphdf1)[18]$colour = 'burlywood1'
V(graphdf1)[19]$colour = 'burlywood2'
E(graphdf1)$weight <- 2*scale(graphdf$total_weight) + 3
par(mar = c(0.3, 0.3, 1, 0.3))
plot(graphdf1,
layout=layout_in_circle,
edge.arrow.size = 0.3,
vertex.size=20,
edge.width = E(graphdf1)$weight,
vertex.color = adjustcolor(V(graphdf1)$colour,alpha.f = .8))
```
```{r}
consumption <- read.csv("Consumption.csv")
```
### Graph2: Top10 cities electricity consumption and housing prices
```{r}
housing = read_csv("housing.csv")
latlong2county <- function(pointsDF) {
# Prepare SpatialPolygons object with one SpatialPolygon
# per county
counties <- map('county', fill=TRUE, col="transparent", plot=FALSE)
IDs <- sapply(strsplit(counties$names, ":"), function(x) x[1])
counties_sp <- map2SpatialPolygons(counties, IDs=IDs,
proj4string=CRS("+proj=longlat +datum=WGS84"))
# Convert pointsDF to a SpatialPoints object
pointsSP <- SpatialPoints(pointsDF[1:2],
proj4string=CRS("+proj=longlat +datum=WGS84"))
# Use 'over' to get _indices_ of the Polygons object containing each point
indices <- over(pointsSP, counties_sp)
# Return the county names of the Polygons object containing each point
countyNames <- sapply(counties_sp@polygons, function(x) x@ID)
countyNames[indices]
}
# Test the function using points in Wisconsin and Oregon.
testPoints <- data.frame(x = c(-90, -120), y = c(44, 44))
housing['county'] = latlong2county(housing)
top10 <- housing %>%
filter(county %in% c("california,los angeles", "california,san diego", "california,riverside",
"california,kern", "california,san bernardino", "california,fresno",
"california,orange", "california,sacramento", "california,san francisco",
"california,santa clara")) %>%
group_by(county) %>%
summarize(avg_price = mean(median_house_value)) %>%
drop_na()
consumption_county <- read.csv("ElectricityByCounty.csv")
temp <- consumption_county %>%
filter(county %in% c("LOS ANGELES", "SAN DIEGO", "RIVERSIDE", "KERN",
"SAN BERNARDINO", "FRESNO", "ORANGE", "SACRAMENTO",
"SAN FRANCISCO", "SANTA CLARA")) %>%
select(county,X2000)
top10['consumption'] = temp['X2000']
```
```{r}
fig <- plot_ly(top10, x = ~county, y = ~consumption, type = "bar", name = "Electricity Consumption") %>%
add_lines(x = ~county, y = ~avg_price, yaxis = "y2", name = "Average Housing Price") %>%
layout(yaxis2 = list(overlaying = "y", side = "right"))
fig
```
### Graph3: Electricity Consumption in LA with Time Series
```{r}
fig <- plot_ly(
type = "scatter",
x = as.Date(consumption$County, format = "%Y"),
y = consumption$LA,
name = 'Electricity Consumption in LA',
mode = "markers",
)
fig <- fig %>%
layout(
title = "Electricity Consumption in LA"
)
fig
```
***
```{r}
consumption
```
```{r}
housing = read_csv("housing.csv")
latlong2county <- function(pointsDF) {
# Prepare SpatialPolygons object with one SpatialPolygon
# per county
counties <- map('county', fill=TRUE, col="transparent", plot=FALSE)
IDs <- sapply(strsplit(counties$names, ":"), function(x) x[1])
counties_sp <- map2SpatialPolygons(counties, IDs=IDs,
proj4string=CRS("+proj=longlat +datum=WGS84"))
# Convert pointsDF to a SpatialPoints object
pointsSP <- SpatialPoints(pointsDF[1:2],
proj4string=CRS("+proj=longlat +datum=WGS84"))
# Use 'over' to get _indices_ of the Polygons object containing each point
indices <- over(pointsSP, counties_sp)
# Return the county names of the Polygons object containing each point
countyNames <- sapply(counties_sp@polygons, function(x) x@ID)
countyNames[indices]
}
# Test the function using points in Wisconsin and Oregon.
testPoints <- data.frame(x = c(-90, -120), y = c(44, 44))
housing['county'] = latlong2county(housing)
housing <- housing %>%
filter(county %in% c("california,los angeles"))
housing$Category[housing$median_house_value<=100000] = '<100K'
housing$Category[housing$median_house_value>100000 & housing$median_house_value<=200000] = '100K~200K'
housing$Category[housing$median_house_value>200000 & housing$median_house_value<=300000] = '200K~300K'
housing$Category[housing$median_house_value>300000 & housing$median_house_value<=400000] = '300K~400K'
housing$Category[housing$median_house_value>400000 ] = '>400K'
```
### Graph4: Los Angeles Housing Prices Distribution With Population.
```{r}
options(warn=-1)
plot_map = ggplot(housing,
aes(x = longitude, y = latitude, color = median_house_value,
hma = housing_median_age, tr = total_rooms, tb = total_bedrooms,
hh = households, mi = median_income)) +
geom_point(aes(size = population), alpha = 0.6) +
xlab("Longitude") +
ylab("Latitude") +
ggtitle("Los Angeles Housing Price Distribution") +
theme(plot.title = element_text(hjust = 0.5)) +
scale_color_viridis(option = "D", labels = comma) +
labs(color = "Median House Value (in $USD)", size = "Population")
plot_map
```
### Graph5: The distribution of housing price amoung ocean proximity in LA
```{r}
fig <- plot_ly(housing, x = ~ocean_proximity, color = ~Category) %>%
add_histogram()
fig <- fig %>%
layout(
title = "The distribution of housing price amoung ocean proximity in LA"
)
fig
```
### Graph6: WordCloud of LA House and Electricity Article
```{r}
text <- readLines('LA_housing_overview.txt')
text <- sapply(text,function(row) iconv(row, "latin1", "ASCII", sub=""))
corpus = VCorpus(VectorSource(text))
corpus = tm_map(corpus, content_transformer(tolower))
corpus = tm_map(corpus, removeNumbers)
corpus = tm_map(corpus, removePunctuation)
corpus = tm_map(corpus, removeWords, stopwords())
#corpus = tm_map(corpus, stemDocument)
corpus = tm_map(corpus, stripWhitespace)
```
```{r}
dtm = DocumentTermMatrix(corpus)
dtm = removeSparseTerms(dtm, 0.9999)
dataset = as.matrix(dtm)
v = sort(colSums(dataset),decreasing=TRUE)
myNames = names(v)
d = data.frame(word=myNames,freq=v)
pal2 <- brewer.pal(8,"Dark2")
wordcloud(d$word, colors = pal2,scale=c(4,.6), random.color=FALSE, d$freq, min.freq=15, max.words=200, random.order=FALSE)
```
